Merge tag 'for-6.19-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - with large folios in use, fix partial incorrect update of a reflinked
   range

 - fix potential deadlock in iget when lookup fails and eviction is
   needed

 - in send, validate inline extent type while detecting file holes

 - fix memory leak after an error when creating a space info

 - remove zone statistics from sysfs again, the output size limitations
   make it unusable, we'll do it in another way in another release

 - test fixes:
     - return proper error codes from block remapping tests
     - fix tree root leaks in qgroup tests after errors

* tag 'for-6.19-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: remove zoned statistics from sysfs
  btrfs: fix memory leaks in create_space_info() error paths
  btrfs: invalidate pages instead of truncate after reflinking
  btrfs: update the Kconfig string for CONFIG_BTRFS_EXPERIMENTAL
  btrfs: send: check for inline extents in range_is_hole_in_parent()
  btrfs: tests: fix return 0 on rmap test failure
  btrfs: tests: fix root tree leak in btrfs_test_qgroups()
  btrfs: release path before iget_failed() in btrfs_read_locked_inode()

Author: torvalds

fs/btrfs/Kconfig

@@ -115,6 +115,10 @@ config BTRFS_EXPERIMENTAL
 
 	  - extent tree v2 - complex rework of extent tracking
 
-	  - large folio support
+	  - large folio and block size (> page size) support
+
+	  - shutdown ioctl and auto-degradation support
+
+	  - asynchronous checksum generation for data writes
 
 	  If unsure, say N.

fs/btrfs/inode.c

@@ -4180,6 +4180,15 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 
 	return 0;
 out:
+	/*
+	 * We may have a read locked leaf and iget_failed() triggers inode
+	 * eviction which needs to release the delayed inode and that needs
+	 * to lock the delayed inode's mutex. This can cause a ABBA deadlock
+	 * with a task running delayed items, as that require first locking
+	 * the delayed inode's mutex and then modifying its subvolume btree.
+	 * So release the path before iget_failed().
+	 */
+	btrfs_release_path(path);
 	iget_failed(vfs_inode);
 	return ret;
 }

fs/btrfs/reflink.c

@@ -705,7 +705,6 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	struct inode *src = file_inode(file_src);
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	int ret;
-	int wb_ret;
 	u64 len = olen;
 	u64 bs = fs_info->sectorsize;
 	u64 end;
@@ -750,25 +749,29 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	btrfs_lock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state);
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
 	btrfs_unlock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state);
+	if (ret < 0)
+		return ret;
 
 	/*
 	 * We may have copied an inline extent into a page of the destination
-	 * range, so wait for writeback to complete before truncating pages
+	 * range, so wait for writeback to complete before invalidating pages
 	 * from the page cache. This is a rare case.
 	 */
-	wb_ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len);
-	ret = ret ? ret : wb_ret;
+	ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len);
+	if (ret < 0)
+		return ret;
+
 	/*
-	 * Truncate page cache pages so that future reads will see the cloned
-	 * data immediately and not the previous data.
+	 * Invalidate page cache so that future reads will see the cloned data
+	 * immediately and not the previous data.
 	 */
-	truncate_inode_pages_range(&inode->i_data,
-				round_down(destoff, PAGE_SIZE),
-				round_up(destoff + len, PAGE_SIZE) - 1);
+	ret = filemap_invalidate_inode(inode, false, destoff, end);
+	if (ret < 0)
+		return ret;
 
 	btrfs_btree_balance_dirty(fs_info);
 
-	return ret;
+	return 0;
 }
 
 static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,

fs/btrfs/send.c

@@ -6383,6 +6383,8 @@ static int range_is_hole_in_parent(struct send_ctx *sctx,
 		extent_end = btrfs_file_extent_end(path);
 		if (extent_end <= start)
 			goto next;
+		if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE)
+			return 0;
 		if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) {
 			search_start = extent_end;
 			goto next;

fs/btrfs/space-info.c

@@ -306,18 +306,22 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags)
 							  0);
 
 		if (ret)
-			return ret;
+			goto out_free;
 	}
 
 	ret = btrfs_sysfs_add_space_info_type(space_info);
 	if (ret)
-		return ret;
+		goto out_free;
 
 	list_add(&space_info->list, &info->space_info);
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
 		info->data_sinfo = space_info;
 
 	return ret;
+
+out_free:
+	kfree(space_info);
+	return ret;
 }
 
 int btrfs_init_space_info(struct btrfs_fs_info *fs_info)

fs/btrfs/sysfs.c

@@ -26,7 +26,6 @@
 #include "misc.h"
 #include "fs.h"
 #include "accessors.h"
-#include "zoned.h"
 
 /*
  * Structure name                       Path
@@ -1189,56 +1188,6 @@ static ssize_t btrfs_commit_stats_store(struct kobject *kobj,
 }
 BTRFS_ATTR_RW(, commit_stats, btrfs_commit_stats_show, btrfs_commit_stats_store);
 
-static ssize_t btrfs_zoned_stats_show(struct kobject *kobj,
-				      struct kobj_attribute *a, char *buf)
-{
-	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
-	struct btrfs_block_group *bg;
-	size_t ret = 0;
-
-
-	if (!btrfs_is_zoned(fs_info))
-		return ret;
-
-	spin_lock(&fs_info->zone_active_bgs_lock);
-	ret += sysfs_emit_at(buf, ret, "active block-groups: %zu\n",
-			     list_count_nodes(&fs_info->zone_active_bgs));
-	spin_unlock(&fs_info->zone_active_bgs_lock);
-
-	mutex_lock(&fs_info->reclaim_bgs_lock);
-	spin_lock(&fs_info->unused_bgs_lock);
-	ret += sysfs_emit_at(buf, ret, "\treclaimable: %zu\n",
-			     list_count_nodes(&fs_info->reclaim_bgs));
-	ret += sysfs_emit_at(buf, ret, "\tunused: %zu\n",
-			     list_count_nodes(&fs_info->unused_bgs));
-	spin_unlock(&fs_info->unused_bgs_lock);
-	mutex_unlock(&fs_info->reclaim_bgs_lock);
-
-	ret += sysfs_emit_at(buf, ret, "\tneed reclaim: %s\n",
-			     str_true_false(btrfs_zoned_should_reclaim(fs_info)));
-
-	if (fs_info->data_reloc_bg)
-		ret += sysfs_emit_at(buf, ret,
-				     "data relocation block-group: %llu\n",
-				     fs_info->data_reloc_bg);
-	if (fs_info->treelog_bg)
-		ret += sysfs_emit_at(buf, ret,
-				     "tree-log block-group: %llu\n",
-				     fs_info->treelog_bg);
-
-	spin_lock(&fs_info->zone_active_bgs_lock);
-	ret += sysfs_emit_at(buf, ret, "active zones:\n");
-	list_for_each_entry(bg, &fs_info->zone_active_bgs, active_bg_list) {
-		ret += sysfs_emit_at(buf, ret,
-				     "\tstart: %llu, wp: %llu used: %llu, reserved: %llu, unusable: %llu\n",
-				     bg->start, bg->alloc_offset, bg->used,
-				     bg->reserved, bg->zone_unusable);
-	}
-	spin_unlock(&fs_info->zone_active_bgs_lock);
-	return ret;
-}
-BTRFS_ATTR(, zoned_stats, btrfs_zoned_stats_show);
-
 static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 				struct kobj_attribute *a, char *buf)
 {
@@ -1651,7 +1600,6 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, bg_reclaim_threshold),
 	BTRFS_ATTR_PTR(, commit_stats),
 	BTRFS_ATTR_PTR(, temp_fsid),
-	BTRFS_ATTR_PTR(, zoned_stats),
 #ifdef CONFIG_BTRFS_EXPERIMENTAL
 	BTRFS_ATTR_PTR(, offload_csum),
 #endif

fs/btrfs/tests/extent-map-tests.c

@@ -1059,19 +1059,22 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info,
 
 	if (out_stripe_len != BTRFS_STRIPE_LEN) {
 		test_err("calculated stripe length doesn't match");
+		ret = -EINVAL;
 		goto out;
 	}
 
 	if (out_ndaddrs != test->expected_mapped_addr) {
 		for (i = 0; i < out_ndaddrs; i++)
 			test_msg("mapped %llu", logical[i]);
 		test_err("unexpected number of mapped addresses: %d", out_ndaddrs);
+		ret = -EINVAL;
 		goto out;
 	}
 
 	for (i = 0; i < out_ndaddrs; i++) {
 		if (logical[i] != test->mapped_logical[i]) {
 			test_err("unexpected logical address mapped");
+			ret = -EINVAL;
 			goto out;
 		}
 	}

fs/btrfs/tests/qgroup-tests.c

@@ -517,11 +517,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 	tmp_root->root_key.objectid = BTRFS_FS_TREE_OBJECTID;
 	root->fs_info->fs_root = tmp_root;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
+	btrfs_put_root(tmp_root);
 	if (ret) {
 		test_err("couldn't insert fs root %d", ret);
 		goto out;
 	}
-	btrfs_put_root(tmp_root);
 
 	tmp_root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(tmp_root)) {
@@ -532,11 +532,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 
 	tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
+	btrfs_put_root(tmp_root);
 	if (ret) {
-		test_err("couldn't insert fs root %d", ret);
+		test_err("couldn't insert subvolume root %d", ret);
 		goto out;
 	}
-	btrfs_put_root(tmp_root);
 
 	test_msg("running qgroup tests");
 	ret = test_no_shared_qgroup(root, sectorsize, nodesize);